So sánh phương pháp

	Mô hình khuếch tán giám sát yếu	Bộ tự mã hóa biến phân
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2022–2024	2014
Người khởi xướng	Ho et al. (DDPM foundation); weak supervision integration by multiple groups, 2022–2024	Kingma, D. P. & Welling, M.
Loại	Generative model with imperfect supervision	Deep generative latent-variable model (encoder–decoder)
Công trình gốc	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
Tên gọi khác	WS-Diffusion, weakly supervised DDPM, label-efficient diffusion model, noisy-label diffusion training	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
Liên quan	6	5
Tóm tắt	A weakly supervised diffusion model trains or conditions a denoising diffusion probabilistic model using coarse, noisy, or incomplete supervision signals — such as image-level class labels, bounding boxes, or crowd-sourced annotations — instead of pixel-precise ground truth. This allows high-quality generative and discriminative outputs in annotation-scarce settings where full labeling is infeasible or prohibitively expensive.	The Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning.